Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     akka
    -0.07
    .addValue
    -0.07
     Ông
    -0.06
    [type
    -0.06
     읽
    -0.06
    Probably
    -0.06
     connectors
    -0.06
    .bind
    -0.06
     확인
    -0.06
     контролю
    -0.06
    POSITIVE LOGITS
     personalities
    0.07
     sailed
    0.06
     intéress
    0.06
    .Tasks
    0.06
     stren
    0.06
    icable
    0.06
    attention
    0.06
    .putInt
    0.06
     будут
    0.06
     Difficulty
    0.06
    Act Density 0.096%

    No Known Activations